T145/ZEUS-8B-V17-abliterated

Full fine-tune vs Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2. Fine-tune: 93% of the weights changed, across 30 of 30 layers.

Tensors changed: Embeddings 0/1, Norms 38/61, MLP 90/90, Attention 117/120, lm_head 1/1

2 derivatives checked

• mradermacher/ZEUS-8B-V17-abliterated-i1-GGUF: Quantization
• mradermacher/ZEUS-8B-V17-abliterated-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse